metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-speech-commands-v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ast-finetuned-speech-commands-bit3
results: []
ast-finetuned-speech-commands-bit3
This model is a fine-tuned version of MIT/ast-finetuned-speech-commands-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4409
- Accuracy: 0.9031
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 36
- eval_batch_size: 36
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 144
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.0583 | 1.0 | 589 | 0.8992 | 0.4810 |
| 0.0628 | 2.0 | 1178 | 0.9031 | 0.4409 |
| 0.0218 | 3.0 | 1767 | 0.9010 | 0.4444 |
| 0.0092 | 4.0 | 2356 | 0.9012 | 0.4322 |
| 0.0148 | 5.0 | 2945 | 0.9031 | 0.3927 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1